Disks and RAID: Profs. Bracy and Van Renesse
Disks and RAID: Profs. Bracy and Van Renesse
Must specify:
• cylinder #
(distance from spindle)
• surface #
• sector #
• transfer size
• memory address
Disk overheads
• Seek time: to get to the track (5-15 millisecs)
• Rotational Latency time: to get to the sector (4-8 millisecs)
• Transfer time: get bits off the disk (25-50 microsecs)
Sector Track
• Version of C-SCAN
• Arm only goes as far as last request in each
direction,
– then reverses direction immediately,
– without first going all the way to the end of the disk.
C-LOOK (Cont.)
Solid State Drives (Flash)
• Most SSDs based on NAND-flash
– other options include DRAM with battery or
NOR gates
NAND Flash
SSD HDD
Cost 10cts/gig 6cts/gig
Power 2-3W 6-7W
Typical Capacity 1TB 2TB
Write Speed 250MB/sec 200MB/sec
Read Speed 700MB/sec 200MB/sec
RAID Motivation
• Disks are improving, but not as fast as CPUs
– 1970s seek time: 50-100 ms.
– 2000s seek time: <5 ms.
– Factor of 20 improvement in 3 decades
• We can use multiple disks for improving performance
– By striping files across multiple disks (placing parts of each file on a
different disk), parallel I/O can improve access time
• Striping reduces reliability
– 100 disks have 1/100th mean time between failures of one disk
• So, we need striping for performance, but we need something to help
with reliability / availability
• To improve reliability, we can add redundancy
RAID
data disks
RAID Level 1
• Mirrored Disks --- data is written to two places
– On failure, just use surviving disk
– In theory, can this detect, and if so, correct bit flip errors??
• Spread read operations across all mirrors
– Write performance is same as single drive
– Read performance is 2x better
• Simple but expensive
Parity disk
data disks
RAID Level 4
• Combines Level 0 and 3 – block-level parity with stripes
• A read accesses just the relevant data disk
• A write accesses all data disks plus the parity disk
– Optimization: can read/write just the data disk and the parity disk, at
the expense of a longer latency. Can you see how?
• Parity disk is a bottleneck for writing
• Also rarely used
Parity disk
data disks
RAID Level 5
• Block Interleaved Distributed Parity
• Like parity scheme, but distribute the parity info over all
disks (as well as data over all disks)
• Better read performance, large write performance
– Reads can outperform SLEDs and RAID-0